© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 1345
    Prev
    Next
    INDEX
    Explanations

    phrases related to conclusions or last steps in a process

    oai_token-act-pair · gpt-3.5-turbo

    the word "finally" in various contexts throughout the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "},"
    -0.73
    hari
    -0.60
    oes
    -0.60
    AME
    -0.59
    lands
    -0.59
    uffer
    -0.58
    pread
    -0.58
    GA
    -0.57
    hist
    -0.57
    Americ
    -0.57
    POSITIVE LOGITS
    itars
    0.75
    icia
    0.72
    intendent
    0.70
     Lastly
    0.70
     FANTASY
    0.66
    姫
    0.65
     srf
    0.64
     Thumbnails
    0.63
    engeance
    0.63
    elvet
    0.63
    Activations Density 0.046%

    No Known Activations